Models/Mistral

Mistral

Mistral models, pricing, and protocols

5 currently available models with pricing synced from the MoleAPI console.

5 models

Compare
M

Mistral model by Mistral for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1
Input$0.7 / 1M tokens
Output$0.7 / 1M tokens
openaiOpenAI compatibleCompare
M

Mistral model by Mistral for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1
Input$0.076 / 1M tokens
Output$0.228 / 1M tokens
Cache read$0.038 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M

Mistral model by Mistral for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1
Input$0.5 / 1M tokens
Output$1.5 / 1M tokens
openaiOpenAI compatibleCompare
M

Mistral model by Mistral for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1
Input$0.02 / 1M tokens
Output$0.06 / 1M tokens
Cache read$0.01 / 1M tokens
discountx0.8
Input$0.016 / 1M tokens
Output$0.048 / 1M tokens
Cache read$0.008 / 1M tokens
relayx0.3
Input$0.006 / 1M tokens
Output$0.018 / 1M tokens
Cache read$0.003 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
M

Mistral model by Mistral for general chat, writing, coding assistance, and tool-assisted workflows.

defaultx1
Input$0.07 / 1M tokens
Output$0.21 / 1M tokens
Cache read$0.035 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare